© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60678
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and elements associated with defining templates and properties in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zaman
    -0.08
    ARRIER
    -0.07
    887
    -0.07
    raquo
    -0.07
    pering
    -0.07
    pectral
    -0.07
    骨
    -0.07
    ghi
    -0.06
    _border
    -0.06
    aine
    -0.06
    POSITIVE LOGITS
    ForObject
    0.07
    .lex
    0.07
     civ
    0.06
     Sole
    0.06
    -backend
    0.06
     íĽĦ기
    0.06
     trá»±c
    0.06
    Dll
    0.06
    .hxx
    0.05
    icari
    0.05
    Activations Density 0.002%

    No Known Activations